Back to leaderboard

qwen3-1.7b

LM-STUDIO GGUF

qwen3 · 1.7B · Q4_K_M

Not Rec.

Mar 7, 2026 · Intel Core™ i5-5300U

llama2:13b

OLLAMA GGUF

llama · 13B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score
19 vs 56
Hardware Fit
64 vs 84
Quality Score
0 vs 44

Hardware

qwen3-1.7b llama2:13b
MachineLENOVO 20BUS00700MacBook Air
CPUIntel Core™ i5-5300UApple M4
Cores410
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500Apple M4
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-1.7b llama2:13b
Tokens/sec5.913.5
First chunk2111 msN/A
TTFT2.1 s415 ms
Load timeN/A0.6 s
Memory usage1.2 GB10.3 GB
Memory %8%32%

HW Fit Score Breakdown

qwen3-1.7b

Speed
21/50
TTFT
19/20
Memory
24/30

llama2:13b

Speed
24/50
TTFT
30/20
Memory
30/30

Quality

qwen3-1.7b

Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

llama2:13b

Reasoning
9/20
Coding
3/20
Instruction
13/20
Structured
7/15
Math
3/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor Multilingual: Strong
View qwen3-1.7b details | View llama2:13b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest